Endre søk
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Scene analysis by mid-level attribute learning using 2D LSTM networks and an application to web-image tagging
University of Kaiserslautern, Kaiserslautern, Germany; German Research Center for Artificial Intelligence (DFKI), Kaiserslautern, Germany.
University of Kaiserslautern, Kaiserslautern, Germany.ORCID-id: 0000-0003-4029-6574
University of Kaiserslautern, Kaiserslautern, Germany.
2015 (engelsk)Inngår i: Pattern Recognition Letters, ISSN 0167-8655, E-ISSN 1872-7344, Vol. 63, s. 23-29Artikkel i tidsskrift (Fagfellevurdert) Published
Abstract [en]

Abstract This paper describes an approach to scene analysis based on supervised training of 2D Long Short-Term Memory recurrent neural networks (LSTM networks). Unlike previous methods, our approach requires no manual construction of feature hierarchies or incorporation of other prior knowledge. Rather, like deep learning approaches using convolutional networks, our recognition networks are trained directly on raw pixel values. However, in contrast to convolutional neural networks, our approach uses 2D LSTM networks at all levels. Our networks yield per pixel mid-level classifications of input images; since training data for such applications is not available in large numbers, we describe an approach to generating artificial training data, and then evaluate the trained networks on real-world images. Our approach performed significantly better than others methods including Convolutional Neural Networks (ConvNet), yet using two orders of magnitude fewer parameters. We further show the experiment on a recently published dataset, outdoor scene attribute dataset for fair comparisons of scene attribute learning which had significant performance improvement (ca. 21%). Finally, our approach is successfully applied on a real-world application, automatic web-image tagging.

sted, utgiver, år, opplag, sider
2015. Vol. 63, s. 23-29
Emneord [en]
LSTM, Mid-level attribute learning, Recurrent neural network, Scene analysis, Web-image tagging
Identifikatorer
URN: urn:nbn:se:ltu:diva-72203DOI: 10.1016/j.patrec.2015.06.003OAI: oai:DiVA.org:ltu-72203DiVA, id: diva2:1271595
Tilgjengelig fra: 2018-12-17 Laget: 2018-12-17 Sist oppdatert: 2019-01-29bibliografisk kontrollert

Open Access i DiVA

fulltext(2043 kB)50 nedlastinger
Filinformasjon
Fil FULLTEXT01.pdfFilstørrelse 2043 kBChecksum SHA-512
27e904ef6d072a8344122eec65bca2119a4a0f1632fdf70fff4548ce694b436ecfb62818dd3ab16bdc8cad2ca3c3e915d398a727e548ffc568f4ce750a11c7f7
Type fulltextMimetype application/pdf

Andre lenker

Forlagets fullteksthttp://www.sciencedirect.com/science/article/pii/S0167865515001634

Søk i DiVA

Av forfatter/redaktør
Liwicki, Marcus
I samme tidsskrift
Pattern Recognition Letters

Søk utenfor DiVA

GoogleGoogle Scholar
Totalt: 50 nedlastinger
Antall nedlastinger er summen av alle nedlastinger av alle fulltekster. Det kan for eksempel være tidligere versjoner som er ikke lenger tilgjengelige

doi
urn-nbn

Altmetric

doi
urn-nbn
Totalt: 44 treff
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf